Triple
T21808014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Bacon Custer |
E538397
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bacon |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Bacon | Statement: [Elizabeth Bacon Custer, familyName, Bacon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bacon Context triple: [Elizabeth Bacon Custer, familyName, Bacon]
-
A.
Bacon
chosen
Bacon is a common English surname historically associated with notable figures such as the philosopher and statesman Francis Bacon.
-
B.
Bacone
Bacone is a small private liberal arts college in Muskogee, Oklahoma, historically affiliated with Native American education and tribal nations.
-
C.
Sausage
Sausage is an American alternative rock side project formed by Primus guitarist Larry LaLonde, known for its experimental, offbeat style.
-
D.
Hammon
Hammon is the surname of Becky Hammon, a prominent basketball coach and former professional player.
-
E.
Lard
Lard is an American industrial metal/punk supergroup best known for featuring Jello Biafra of Dead Kennedys collaborating with members of Ministry.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f078047ca88190a0efa4bc7f2faf80 |
completed | April 28, 2026, 9:04 a.m. |
Created at: April 16, 2026, 6:53 p.m.